End of training

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8681
-- Rouge1: 0.4331
-- Rouge2: 0.123
-- Rougel: 0.2315
-- Rougelsum: 0.2321
+- Loss: 2.4758
+- Rouge1: 0.3972
+- Rouge2: 0.1525
+- Rougel: 0.2279
+- Rougelsum: 0.2297
 - Gen Len: 142.0
 
 ## Model description
@@ -42,29 +42,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 2.8335        | 1.0   | 10   | 2.4176          | 0.3799 | 0.1235 | 0.228  | 0.2282    | 135.0   |
-| 2.2104        | 2.0   | 20   | 2.3294          | 0.4484 | 0.1556 | 0.2797 | 0.2805    | 79.6    |
-| 1.8803        | 3.0   | 30   | 2.3395          | 0.3481 | 0.1124 | 0.224  | 0.2274    | 96.0    |
-| 1.6309        | 4.0   | 40   | 2.3934          | 0.4373 | 0.126  | 0.2457 | 0.2444    | 142.0   |
-| 1.4263        | 5.0   | 50   | 2.4567          | 0.3681 | 0.1245 | 0.2353 | 0.2342    | 71.0    |
-| 1.2476        | 6.0   | 60   | 2.5688          | 0.3997 | 0.135  | 0.2588 | 0.2564    | 79.0    |
-| 1.1164        | 7.0   | 70   | 2.6860          | 0.3988 | 0.1141 | 0.2296 | 0.2298    | 142.0   |
-| 1.0058        | 8.0   | 80   | 2.7666          | 0.4679 | 0.1486 | 0.2654 | 0.2675    | 142.0   |
-| 0.9275        | 9.0   | 90   | 2.8439          | 0.4362 | 0.1232 | 0.2415 | 0.2414    | 142.0   |
-| 0.8801        | 10.0  | 100  | 2.8681          | 0.4331 | 0.123  | 0.2315 | 0.2321    | 142.0   |
+| 2.8064        | 1.0   | 10   | 2.5907          | 0.3676 | 0.08   | 0.1808 | 0.1804    | 136.0   |
+| 2.4065        | 2.0   | 20   | 2.5102          | 0.3116 | 0.0669 | 0.1732 | 0.1732    | 142.0   |
+| 2.2329        | 3.0   | 30   | 2.4821          | 0.3931 | 0.108  | 0.2077 | 0.2074    | 142.0   |
+| 2.1376        | 4.0   | 40   | 2.4786          | 0.3972 | 0.1525 | 0.2279 | 0.2297    | 142.0   |
+| 2.0733        | 5.0   | 50   | 2.4758          | 0.3972 | 0.1525 | 0.2279 | 0.2297    | 142.0   |
 
 
 ### Framework versions